---
library_name: transformers
license: apache-2.0
base_model: HooshvareLab/bert-fa-zwnj-base
tags:
- generated_from_trainer
model-index:
- name: parsbert-persianQA
  results: []
datasets:
- azizmatin/question_answering
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# parsbert-persianQA

This model is a fine-tuned version of [HooshvareLab/bert-fa-zwnj-base](https://huggingface.co./HooshvareLab/bert-fa-zwnj-base) on [azizmatin/question_answering](https://huggingface.co./datasets/azizmatin/question_answering) dataset.
It achieves the following results on the evaluation set:
- Loss: 3.4521

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 2.8464        | 1.0   | 9205  | 2.5020          |
| 2.1887        | 2.0   | 18410 | 2.6621          |
| 1.2823        | 3.0   | 27615 | 3.4521          |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1